Timezone: »

Semi-supervised Deep Kernel Learning: Regression with Unlabeled Data by Minimizing Predictive Variance
Neal Jean · Sang Michael Xie · Stefano Ermon

Thu Dec 06 07:45 AM -- 09:45 AM (PST) @ Room 517 AB #142

Large amounts of labeled data are typically required to train deep learning models. For many real-world problems, however, acquiring additional data can be expensive or even impossible. We present semi-supervised deep kernel learning (SSDKL), a semi-supervised regression model based on minimizing predictive variance in the posterior regularization framework. SSDKL combines the hierarchical representation learning of neural networks with the probabilistic modeling capabilities of Gaussian processes. By leveraging unlabeled data, we show improvements on a diverse set of real-world regression tasks over supervised deep kernel learning and semi-supervised methods such as VAT and mean teacher adapted for regression.

Author Information

Neal Jean (Stanford University)
Sang Michael Xie (Stanford University)
Stefano Ermon (Stanford)

More from the Same Authors